CUSTOMER SUPPORT
Flag Live Intercom Chats With No Help Article and Alert Slack
When an Intercom conversation closes, checks whether the customer's question is already covered by a help article.
How it runs
The automated pipeline, trigger to output.
- TriggerIntercom conversation closedIntercom
- ActionFetch conversation transcriptIntercom
- ActionSummarize question and title with OpenAIOpenAI
- ActionSearch ReadMe for matching articleReadMe
- LogicExit if already covered
- OutputPost gap to Slack triage channelSlack
What it does
Catches knowledge-base gaps the moment they happen. Each time an Intercom conversation is resolved, it extracts the core question, searches your published articles for a match, and if nothing covers it, posts a flagged gap into Slack so the content owner can decide whether it's worth a new article.
When to use it
Use this when you want a real-time signal of which questions your docs don't answer, rather than a weekly batch. Ideal for fast-moving products where new gaps appear daily and you want them surfaced while context is fresh.
How it works
- 1An Intercom conversation-closed event triggers the run.
- 2Pull the full conversation transcript from Intercom.
- 3OpenAI summarizes the customer's underlying question and proposes an article title.
- 4Search ReadMe for an existing article covering that question.
- 5A logic step exits silently if a strong match already exists.
- 6For uncovered questions, post a Slack message to the triage channel with the question, suggested title, and a link back to the conversation.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ReadMeAPI docs, changelog, auth.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Customer Support workflows
Negative VIP CSAT to Owner Callback Scheduler
When a VIP submits a low Intercom CSAT rating, drafts a recovery note with an LLM and books a callback on the account owner's Google Calendar within their working hours.
CEO Agent: Mine Last Month's Tickets and Publish a Deflection Plan
Monthly, an agent investigates the top recurring Zendesk ticket themes, drafts and publishes the highest-confidence help articles to ReadMe.
Mine a Discord Support Channel for Recurring Questions to Document
On a daily schedule, scans a Discord support channel for questions the community keeps asking, deduplicates against existing ReadMe docs.
Daily VIP Sentiment Digest for Account Owners
Each morning, pulls the prior day's Intercom conversations for VIP accounts, summarizes the overall mood per account with an LLM.
VIP Reply Sentiment Watcher with Account-Owner Escalation
Scores every inbound Intercom reply from a VIP customer for frustration and, when it crosses the anger threshold, pings the account owner in Slack with the conversation link…
Frustrated VIP Reply to Linear Escalation Ticket
When a VIP customer's Intercom reply reads as angry, opens a prioritized Linear issue with the conversation transcript, sentiment score, and account owner assigned.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.